{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/multimedeval-a-benchmark-and-a-toolkit-for","title":"MultiMedEval: A Benchmark and a Toolkit for Evaluating Medical Vision-Language Models","arxiv_id":"2402.09262","date":"2024-02-14","proceeding":null,"authors":["Corentin Royer","Bjoern Menze","Anjany Sekuboyina"],"abstract":"We introduce MultiMedEval, an open-source toolkit for fair and reproducible evaluation of large, medical vision-language models (VLM). MultiMedEval comprehensively assesses the models' performance on a broad array of six multi-modal tasks, conducted over 23 datasets, and spanning over 11 medical domains. The chosen tasks and performance metrics are based on their widespread adoption in the community and their diversity, ensuring a thorough evaluation of the model's overall generalizability. We open-source a Python toolkit (github.com/corentin-ryr/MultiMedEval) with a simple interface and setup process, enabling the evaluation of any VLM in just a few lines of code. Our goal is to simplify the intricate landscape of VLM evaluation, thus promoting fair and uniform benchmarking of future models.","url_abs":"https://arxiv.org/abs/2402.09262v2","url_pdf":"https://arxiv.org/pdf/2402.09262v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"multimedeval-a-benchmark-and-a-toolkit-for","repo_url":"https://github.com/corentin-ryr/multimedeval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"diversity","task_name":"Diversity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.09262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09262"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/corentin-ryr/multimedeval","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"90ae9e40f89c7167","entry":"get_correct_answer","repo":"corentin-ryr/multimedeval","repo_kind":"official","path":"multimedeval/dynamic_datasets.py","file_url":"https://github.com/corentin-ryr/multimedeval/blob/HEAD/multimedeval/dynamic_datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"90ae9e40f89c7167"}},{"code_sha256_prefix":"c0a05cc29f287b7c","entry":"make_constructor","repo":"corentin-ryr/multimedeval","repo_kind":"official","path":"multimedeval/dynamic_datasets.py","file_url":"https://github.com/corentin-ryr/multimedeval/blob/HEAD/multimedeval/dynamic_datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c0a05cc29f287b7c"}},{"code_sha256_prefix":"3c28edb934eaa0c8","entry":"compute_meteor","repo":"corentin-ryr/multimedeval","repo_kind":"official","path":"multimedeval/report_comparison_utils.py","file_url":"https://github.com/corentin-ryr/multimedeval/blob/HEAD/multimedeval/report_comparison_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c28edb934eaa0c8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}